Token导航 LogoToken导航

Agent Skill · 研究检索

vault-cleanup-auditor(金库清理审核员)

用于辅助安全审计、权限检查、凭据风险、认证流程和常见漏洞排查。它适合让 Agent 梳理敏感配置、检查依赖风险、分析鉴权逻辑或生成安全复核清单。使用时不能把工具输出直接当最终结论,涉及密钥、令牌、用户数据或生产系统时,应先确认最小权限、脱敏方式和操作边界。

vault-cleanup-auditor 是研究检索类 Agent Skill,可用宿主为 Codex、Claude、Cursor、Gemini CLI,通过GitHub 仓库获取,权限为执行命令;许可证信息还不明确,第三方扫描已通过,按安装量在研究检索类的 73,675 个 Skill 里排第 41,736。

总安装 1,148周安装 46GitHub Stars 262下载 372核验 2026-05-01

安装说明

本站只整理中文说明,不托管安装包,也不代用户安装。
GitHub
许可证
unknown

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:vault-cleanup-auditor(金库清理审核员)
来源仓库:https://github.com/brianrwagner/ai-marketing-skills
仓库路径:skills/vault-cleanup-auditor
安装命令:
npx skills add https://github.com/brianrwagner/ai-marketing-skills --skill vault-cleanup-auditor
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 npx skills 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

skills.shnpx skills
npx skills add https://github.com/brianrwagner/ai-marketing-skills --skill vault-cleanup-auditor

这个 Skill 是做什么的

研究检索类 Skill 主要解决「找资料、核对事实、把来源整理清楚」的问题,通常会让助手先检索再总结。

vault-cleanup-auditor 对 Obsidian 知识库运行四项定向检查并生成优先级审计报告。适用于定期维护知识库结构和内容质量。无需 API 或付费服务,30秒内完成本地分析。操作前应确认 vault 路径权限,避免影响生产环境数据。

适用宿主包括 Codex、Claude、Cursor、Gemini CLI,接入前应确认版本、权限和运行环境要求。

来源仓库内路径:skills/vault-cleanup-auditor

上手步骤

4 步
  1. 1

    确认自己的宿主工具

    公开资料标注支持 Codex、Claude、Cursor、Gemini CLI;先确认自己用的是其中之一,再按对应工具的 Skills 目录放置。

  2. 2

    拿到安装命令

    可以直接复制的命令是 npx skills add https://github.com/brianrwagner/ai-marketing-skills --skill vault…;命令里的占位符换成自己的路径或密钥再执行。

  3. 3

    安装后重启宿主

    命令执行完要完全退出宿主工具再打开,让新装的 Skill 被重新扫描到,否则列表里可能看不到。

  4. 4

    按最小权限试用

    它需要执行命令,先在测试目录或测试账号里跑,确认没问题再放到正式项目。

常见问题

6 条

vault-cleanup-auditor 怎么安装?

在终端执行 npx skills add https://github.com/brianrwagner/ai-marketing-skills --skill vault-cleanup-a…。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

vault-cleanup-auditor 支持哪些 AI 工具?

公开资料标注支持 Codex、Claude、Cursor、Gemini CLI。其他工具只要能读取本地 Skill 目录,一般也能手动放进去,但要自己确认触发方式是否一致。

vault-cleanup-auditor 需要什么权限?

权限级别是执行命令。安装流程涉及命令执行,可能通过 npx skills add https://github.com/brianrwagner/ai-marketing-skills --skill vault-cleanup-auditor 联网下载 Skill 或依赖。用户安装前应确认命令来源、仓库内容和执行环境。

vault-cleanup-auditor 是免费的吗?

公开资料没有标注明确许可证,收费和商用限制都无法确认。正式使用前请到来源仓库核对授权说明。

vault-cleanup-auditor 用的人多吗?

公开数据是累计安装 1,148 次,近一周安装 46 次,下载 372 次,GitHub 262 星。这些数字来自第三方目录统计,只能当作热度参考,不代表质量或安全性。

vault-cleanup-auditor 安全吗?

第三方扫描结果为通过,但这只覆盖已知的静态检查项,不能替代自己读一遍源码和安装命令。

值得选的地方和要先想清楚的地方

值得选的地方

  • 同时适配 4 种工具,换客户端不用重新找替代品。
  • 第三方扫描已通过,常见的高风险行为没有命中。

先想清楚的地方

  • 需要执行命令,装到常用环境前要先评估影响面。
  • 许可证没有明确标注,能不能商用、能不能再分发都不确定。
  • 第三方目录整理,版本更新和行为细节以来源仓库为准。

适不适合你

更适合

  • 已经在用 Codex,想直接扩展它能力的人。
  • 需要处理研究检索类任务、又不想每次都手写提示词的人。

不太适合

  • 不能接受 Skill 在你机器上执行命令的人。
  • 需要明确授权才能用到公司项目里的场景。
  • 需要厂商级技术支持和 SLA 的生产系统。

研究检索类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
find-skills

寻找技能 · Codex、Claude

31,199,81316,486操作浏览器MIT有提醒
self-improving-agent

自我改进 Agent · OpenClaw

16,464,0023,396接触敏感数据MIT-0通过
soultrace

灵魂追踪 · Codex、Claude

7,588,94412需要联网未明确有提醒
self-improving

自我完善 · OpenClaw

6,829,2841,046需要联网MIT-0通过
microsoft-foundry

微软代工厂 · Codex、Claude

6,614,144764调用外部服务未明确有提醒
vault-cleanup-auditor

金库清理审核员 · 本页

1,148262执行命令未明确通过

按安装量取同分类前几名;数字来自第三方目录统计,只作热度参考,不代表质量结论。

SKILL.md 原文

Vault Cleanup Auditor

Runs 4 targeted checks against your Obsidian vault and saves a prioritized audit report to vault-audit/YYYY-MM-DD-audit.md. Takes under 30 seconds. No APIs, no paid services.

Run it monthly or whenever the vault starts feeling messy.


How to Use

Open Claude Code and say:

Run the Vault Cleanup Auditor skill against my vault at /path/to/vault.

Skill Instructions (for Claude Code)

When this skill is invoked, follow these phases exactly.


PHASE 1: INTAKE

Check whether the user has provided:

  • vault_path — absolute path to their Obsidian vault root

If missing, ask:

What's the absolute path to your Obsidian vault? (e.g. /root/obsidian-vault)

Do not proceed until confirmed.


PHASE 2: ANALYZE

Run all 4 checks. Capture raw output from each before writing the report.

Check 1 — Stale drafts (30+ days, unposted):

VAULT="VAULT_PATH_HERE"
echo "=== CHECK 1: STALE DRAFTS ==="
find "$VAULT/content/ready-to-post" -name "*.md" -mtime +30 2>/dev/null | while read f; do
  if grep -q '\*\*Posted:\*\* ❌' "$f" 2>/dev/null; then
    days=$(( ($(date +%s) - $(stat -c %Y "$f")) / 86400 ))
    echo "${days}d|${f##$VAULT/}"
  fi
done
echo "=== END CHECK 1 ==="

Check 2 — Incomplete files (no headings, 5+ lines):

VAULT="VAULT_PATH_HERE"
echo "=== CHECK 2: INCOMPLETE FILES ==="
find "$VAULT" -name "*.md" \
  -not -path "*/.git/*" \
  -not -path "*/.obsidian/*" \
  -not -path "*/.openclaw/*" | while read f; do
  if ! grep -qE '^#{1,6} ' "$f" 2>/dev/null; then
    lines=$(wc -l < "$f")
    if [ "$lines" -gt 5 ]; then
      echo "${lines}lines|${f##$VAULT/}"
    fi
  fi
done
echo "=== END CHECK 2 ==="

Check 3 — Duplicate filenames:

VAULT="VAULT_PATH_HERE"
echo "=== CHECK 3: DUPLICATE FILENAMES ==="
find "$VAULT" -name "*.md" \
  -not -path "*/.git/*" \
  -not -path "*/.obsidian/*" \
  -not -path "*/.openclaw/*" \
  -printf "%f\n" | sort | uniq -d | while read name; do
  echo "DUPE:$name"
  find "$VAULT" -name "$name" \
    -not -path "*/.git/*" \
    -not -path "*/.obsidian/*" | while read f; do
    echo "  PATH:${f##$VAULT/}"
  done
done
echo "=== END CHECK 3 ==="

Check 4 — Empty folders:

VAULT="VAULT_PATH_HERE"
echo "=== CHECK 4: EMPTY FOLDERS ==="
find "$VAULT" -type d -empty \
  -not -path "*/.git/*" \
  -not -path "*/.obsidian/*" \
  -not -path "*/.openclaw/*" | while read d; do
  echo "${d##$VAULT/}/"
done
echo "=== END CHECK 4 ==="

PHASE 3: OUTPUT

3a. Create the report directory and file:

VAULT="VAULT_PATH_HERE"
DATE=$(date +%Y-%m-%d)
mkdir -p "$VAULT/vault-audit"
REPORT="$VAULT/vault-audit/${DATE}-audit.md"
echo "Report path: $REPORT"

3b. Write the report using this exact structure:

# Vault Cleanup Audit — YYYY-MM-DD

Generated: YYYY-MM-DD HH:MM

**Summary:** 🔴 [N] stale | 🟡 [N] incomplete | 🟡 [N] dupes | 🟢 [N] empty

---

## 🔴 Stale Drafts (30+ days, unposted)

- [Nd old] path/to/file.md
[cap at 15 items — add "...and N more" if over]

## 🟡 Incomplete Files (no headings, 5+ lines)

- path/to/file.md (N lines)
[cap at 15]

## 🟡 Duplicate Filenames

- **filename.md**
  - path/one/filename.md
  - path/two/filename.md
[cap at 15 duplicate names]

## 🟢 Empty Folders

- path/to/folder/
[cap at 15]

---

**What to do:**
- 🔴 Stale drafts: post them, delete them, or archive to `content/posted/`
- 🟡 Incomplete files: finish or trash
- 🟡 Duplicates: merge or rename the less important one
- 🟢 Empty folders: safe to delete (or keep if you're about to use them)

3c. Print the summary to terminal:

✅ Audit saved to: vault-audit/YYYY-MM-DD-audit.md

Summary:
🔴 [N] stale drafts
🟡 [N] incomplete files
🟡 [N] duplicate filenames
🟢 [N] empty folders

PHASE 4: SELF-CRITIQUE

Before finalizing, check:

  1. All 4 checks ran — Confirm output exists between each === CHECK N === / === END CHECK N === marker. If a check produced no output, note "0 issues found" in the report — do not skip the section.
  2. Counts are accurate — The summary line counts must match the actual items listed in each section. Re-count if unsure.
  3. Report saved correctly — Confirm the file exists at vault-audit/YYYY-MM-DD-audit.md. If the write failed, report the error and provide the report content inline.
  4. No blank sections — Every section must either list items OR say "No issues found." Never leave a section header with nothing below it.

Fix any failures before delivering the final output.


Example Report

# Vault Cleanup Audit — 2026-03-01

Generated: 2026-03-01 08:14

**Summary:** 🔴 3 stale | 🟡 2 incomplete | 🟡 1 dupe | 🟢 2 empty

---

## 🔴 Stale Drafts (30+ days, unposted)

- [47d old] content/ready-to-post/linkedin/2026-01-12-ai-systems-post.md
- [38d old] content/ready-to-post/twitter/2026-01-21-founder-ops.md
- [31d old] content/ready-to-post/newsletter/2026-01-28-tools-roundup.md

## 🟡 Incomplete Files (no headings, 5+ lines)

- bambf/research/untitled-notes.md (23 lines)
- thinking/random-thoughts.md (11 lines)

## 🟡 Duplicate Filenames

- **README.md**
  - bambf/brand/README.md
  - bambf/tracking/README.md

## 🟢 Empty Folders

- content/queue/rejected/
- bambf/clients/archived/

---

**What to do:**
- 🔴 Stale drafts: post them, delete them, or archive to `content/posted/`
- 🟡 Incomplete files: finish or trash
- 🟡 Duplicates: merge or rename the less important one
- 🟢 Empty folders: safe to delete (or keep if you're about to use them)

Requirements

  • Claude Code with bash tool access
  • Bash + standard Unix tools: find, grep, wc, stat, date, awk
  • Read access to vault directory
  • Write access to vault-audit/ inside the vault (auto-created)
  • No APIs, no paid services, no external dependencies

平台分布

Codex

36.06%
按下载量换算134

Claude

29.88%
按下载量换算111

Cursor

18.98%
按下载量换算71

Gemini CLI

10.53%
按下载量换算39

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

通过

权限和风险

执行命令

安装流程涉及命令执行,可能通过 npx skills add https://github.com/brianrwagner/ai-marketing-skills --skill vault-cleanup-auditor 联网下载 Skill 或依赖。用户安装前应确认命令来源、仓库内容和执行环境。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。目前只有一个公开来源,建议同时核对源仓库。

继续浏览同类 Skills